I try to adjust hyperparameter by create trainer_config.yaml file. Detail is here
behaviors: EscapeRoom: trainer_type: ppo hyperparameters: batch_size: 2048 buffer_size: 20480 learning_rate: 0.0003 beta: 0.005 epsilon: 0.2 lambd: 0.95 num_epoch: 3 learning_rate_schedule: linear network_settings: normalize: false hidden_units: 256 num_layers: 2 vis_encode_type: simple reward_signals: extrinsic: gamma: 0.99 strength: 1.0 keep_checkpoints: 5 checkpoint_interval: 500000 max_steps: 5000000 time_horizon: 128 summary_freq: 10000 threaded: true
But when I run in terminal mlagents-learn /(config_paht)/trainer_config.yaml --run-id=test, it show the error below
File “/Users/poramat/opt/anaconda3/bin/mlagents-learn”, line 8, in
sys.exit(main())
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/learn.py”, line 264, in main
run_cli(parse_command_line())
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/learn.py”, line 260, in run_cli
run_training(run_seed, options, num_areas)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/learn.py”, line 136, in run_training
tc.start_learning(env_manager)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents_envs/timers.py”, line 305, in wrapped
return func(*args, **kwargs)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/trainer_controller.py”, line 172, in start_learning
self._reset_env(env_manager)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents_envs/timers.py”, line 305, in wrapped
return func(*args, **kwargs)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/trainer_controller.py”, line 107, in _reset_env
self._register_new_behaviors(env_manager, env_manager.first_step_infos)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/trainer_controller.py”, line 267, in _register_new_behaviors
self._create_trainers_and_managers(env_manager, new_behavior_ids)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/trainer_controller.py”, line 165, in _create_trainers_and_managers
self._create_trainer_and_manager(env_manager, behavior_id)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/trainer_controller.py”, line 125, in _create_trainer_and_manager
trainer = self.trainer_factory.generate(brain_name)
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/trainer/trainer_factory.py”, line 57, in generate
trainer_settings = self.trainer_config[behavior_name]
File “/Users/poramat/opt/anaconda3/lib/python3.9/site-packages/mlagents/trainers/settings.py”, line 732, in missing
raise TrainerConfigError(
mlagents.trainers.exception.TrainerConfigError: The behavior name Roll agent has not been specified in the trainer configuration. Please add an entry in the configuration file for Roll agent, or set default_settings.
I try to fix it by using the follow comment from this forum [https://forum.unity.com/threads/trainerconfigerror-the-option-default-was-specified-in-your-yaml-file-but-is-invalid.912671/] but it still not working. How can I do?